claude-synod-debate

When one AI isn't enough, convene the council.

English · 한국어

%%{init: {'theme': 'dark', 'themeVariables': { 'primaryColor': '#1e3a5f', 'secondaryColor': '#4a1d1d', 'tertiaryColor': '#1a3d1a'}}}%%
flowchart TB
    subgraph ACT1["🎬 ACT I · SOLVE"]
        G1["🔵 Gemini → Solution A"]
        O1["🟢 OpenAI → Solution B"]
    end

    subgraph ACT2["⚔️ ACT II · CRITIQUE"]
        G2["🔵 Gemini attacks B"]
        O2["🟢 OpenAI attacks A"]
    end

    subgraph ACT3["⚖️ ACT III · VERDICT"]
        C["🟠 Claude → Final Answer"]
    end

    ACT1 --> ACT2 --> ACT3

    style ACT1 fill:#1e3a5f,stroke:#3b82f6,stroke-width:2px,color:#fff
    style ACT2 fill:#4a1d1d,stroke:#ef4444,stroke-width:2px,color:#fff
    style ACT3 fill:#1a3d1a,stroke:#22c55e,stroke-width:2px,color:#fff

# 1️⃣ Install the plugin
/plugin install quantsquirrel/claude-synod-debate

# 2️⃣ Set your API keys (one-time)
export GEMINI_API_KEY="your-gemini-key"
export OPENAI_API_KEY="your-openai-key"

# 3️⃣ Run setup (installs deps, configures CLI tools, tests models)
/synod-setup

# 4️⃣ Summon the council
/synod review Is this authentication flow secure?

That's it. The council convenes automatically.

/synod-setup

[Synod Setup] 초기 설정을 시작합니다...

Step 0/4: Python 의존성 확인
  ✓ google-genai 설치됨
  ✓ openai 설치됨
  ✓ httpx 설치됨

Step 1/4: CLI 도구 확인
  ✓ gemini-3.py
  ✓ openai-cli.py

Step 2/4: API 키 확인
  ✓ GOOGLE_API_KEY (설정됨)
  ✓ OPENAI_API_KEY (설정됨)

Step 3/4: MCP 라우팅 호환성 확인
  ✓ MCP 라우팅 미감지

Step 4/4: 모델 응답 시간 측정 (타임아웃: 120초)

Provider    Model              Latency    Status
───────────────────────────────────────────────
gemini      flash              3.2초      ✓ 권장
gemini      pro                12.4초     ✓ 사용 가능
openai      gpt4o              2.8초      ✓ 권장
openai      o3                 45.2초     ⚠ 느림

[완료] 4/4 모델 사용 가능
Synod를 사용할 준비가 되었습니다!

# Optional: Add more providers to your council
export DEEPSEEK_API_KEY="your-deepseek-key"   # DeepSeek R1
export GROQ_API_KEY="your-groq-key"           # Groq LPU
export OPENROUTER_API_KEY="your-openrouter-key" # OpenRouter (Recommended)

# Opt-in Providers (requires explicit activation)
# Grok (2M context window)
export SYNOD_ENABLE_GROK=1
export XAI_API_KEY="your-xai-key"

# Mistral (code specialization)
export SYNOD_ENABLE_MISTRAL=1
export MISTRAL_API_KEY="your-mistral-key"

# Code review
/synod review "Is this recursive function O(n) or O(n²)?"

# System design
/synod design "Design a rate limiter for 10M requests/day"

# Debugging
/synod debug "Why does this only fail on Tuesdays?"

# Brainstorming
/synod idea "How do we reduce checkout abandonment?"

Synod calculates trust using the CortexDebate formula:

                Credibility × Reliability × Intimacy
Trust Score = ────────────────────────────────────────
                      Self-Orientation

Interpretation:

• T ≥ 1.5 → Primary source (high trust)
• T ≥ 1.0 → Reliable input
• T ≥ 0.5 → Consider with caution
• T < 0.5 → Excluded from synthesis

# Install plugin
/plugin install quantsquirrel/claude-synod-debate

# Set API keys
export GEMINI_API_KEY="your-gemini-key"
export OPENAI_API_KEY="your-openai-key"

# Run setup (auto-installs Python deps, creates CLI wrappers, tests models)
/synod-setup

/synod-setup handles everything: Python dependencies (google-genai, openai, httpx), CLI tool wrappers in ~/.synod/bin/, API key validation, and model connectivity testing.

git clone https://github.com/quantsquirrel/claude-synod-debate.git
cd claude-synod-debate
pip install google-genai openai httpx
cp skills/*.md ~/.claude/commands/

# Run setup to create CLI wrappers and test models
python3 tools/synod-setup.py

# Required
export GEMINI_API_KEY="your-gemini-key"
export OPENAI_API_KEY="your-openai-key"

# Optional
export SYNOD_SESSION_DIR="~/.synod/sessions"
export SYNOD_RETENTION_DAYS=30

Synod executes external models (Gemini, OpenAI) exclusively via CLI tools (gemini-3, openai-cli). If your environment includes MCP routing plugins that redirect model calls through ask_codex or ask_gemini, Synod's built-in defense-in-depth guards prevent interception:

1. allowed-tools frontmatter — Schema-level restriction excludes MCP tools
2. Markdown directives — Explicit prohibition in skill entry point and Phase 0/1
3. Automated tests — CI validates guard presence against configuration drift

No additional configuration needed — protection is automatic.

• MCP Server — Native Claude Code integration
• VS Code Extension — GUI for debate visualization
• Knowledge Base — Learning from debate history
• Web Dashboard — Real-time debate monitoring
• More LLMs — Llama, Mistral, Claude variants v3.0: 7 providers supported!

@software{synod2026,
  title   = {Synod: Multi-Agent Deliberation for Claude Code},
  author  = {quantsquirrel},
  year    = {2026},
  url     = {https://github.com/quantsquirrel/claude-synod-debate}
}